Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Chen-Yu, Chen, Kuan-Cheng, Murota, Keisuke, Chen, Samuel Yen-Chi, Rinaldi, Enrico
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.13054
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916905648914432
author Liu, Chen-Yu
Chen, Kuan-Cheng
Murota, Keisuke
Chen, Samuel Yen-Chi
Rinaldi, Enrico
author_facet Liu, Chen-Yu
Chen, Kuan-Cheng
Murota, Keisuke
Chen, Samuel Yen-Chi
Rinaldi, Enrico
contents Knowledge distillation (KD) is a widely adopted technique for compressing large models into smaller, more efficient student models that can be deployed on devices with limited computational resources. Among various KD methods, Relational Knowledge Distillation (RKD) improves student performance by aligning relational structures in the feature space, such as pairwise distances and angles. In this work, we propose Quantum Relational Knowledge Distillation (QRKD), which extends RKD by incorporating quantum relational information. Specifically, we map classical features into a Hilbert space, interpret them as quantum states, and compute quantum kernel values to capture richer inter-sample relationships. These quantum-informed relations are then used to guide the distillation process. We evaluate QRKD on both vision and language tasks, including CNNs on MNIST and CIFAR-10, and GPT-2 on WikiText-2, Penn Treebank, and IMDB. Across all benchmarks, QRKD consistently improves student model performance compared to classical RKD. Importantly, both teacher and student models remain classical and deployable on standard hardware, with quantum computation required only during training. This work presents the first demonstration of quantum-enhanced knowledge distillation in a fully classical deployment setting.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13054
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantum Relational Knowledge Distillation
Liu, Chen-Yu
Chen, Kuan-Cheng
Murota, Keisuke
Chen, Samuel Yen-Chi
Rinaldi, Enrico
Quantum Physics
Knowledge distillation (KD) is a widely adopted technique for compressing large models into smaller, more efficient student models that can be deployed on devices with limited computational resources. Among various KD methods, Relational Knowledge Distillation (RKD) improves student performance by aligning relational structures in the feature space, such as pairwise distances and angles. In this work, we propose Quantum Relational Knowledge Distillation (QRKD), which extends RKD by incorporating quantum relational information. Specifically, we map classical features into a Hilbert space, interpret them as quantum states, and compute quantum kernel values to capture richer inter-sample relationships. These quantum-informed relations are then used to guide the distillation process. We evaluate QRKD on both vision and language tasks, including CNNs on MNIST and CIFAR-10, and GPT-2 on WikiText-2, Penn Treebank, and IMDB. Across all benchmarks, QRKD consistently improves student model performance compared to classical RKD. Importantly, both teacher and student models remain classical and deployable on standard hardware, with quantum computation required only during training. This work presents the first demonstration of quantum-enhanced knowledge distillation in a fully classical deployment setting.
title Quantum Relational Knowledge Distillation
topic Quantum Physics
url https://arxiv.org/abs/2508.13054